@inproceedings{ye-etal-2025-genpilot,
    title = "{G}en{P}ilot: A Multi-Agent System for Test-Time Prompt Optimization in Image Generation",
    author = "Ye, Wen  and
      Liu, Zhaocheng  and
      Yuwei, Gui  and
      Yuan, Tingyu  and
      Su, Yunyue  and
      Fang, Bowen  and
      Zhao, Chaoyang  and
      Liu, Qiang  and
      Wang, Liang",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.49/",
    doi = "10.18653/v1/2025.findings-emnlp.49",
    pages = "929--958",
    ISBN = "979-8-89176-335-7",
    abstract = "Text-to-image synthesis has made remarkable progress, yet accurately interpreting complex and lengthy prompts remains challenging, often resulting in semantic inconsistencies and missing details. Existing solutions, such as fine-tuning, are model-specific and require training, while prior automatic prompt optimization (APO) approaches typically lack systematic error analysis and refinement strategies, resulting in limited reliability and effectiveness. Meanwhile, test-time scaling methods operate on fixed prompts and on noise or sample numbers, limiting their interpretability and adaptability. To solve these, we introduce a flexible and efficient test-time prompt optimization strategy that operates directly on the input text. We propose a plug-and-play multi-agent system called GenPilot, integrating error analysis, clustering-based adaptive exploration, fine-grained verification, and a memory module for iterative optimization. Our approach is model-agnostic, interpretable, and well-suited for handling long and complex prompts. Simultaneously, we summarize the common patterns of errors and the refinement strategy, offering more experience and encouraging further exploration. Experiments on DPG-bench and Geneval with improvements of up to 16.9{\%} and 5.7{\%} demonstrate the strong capability of our methods in enhancing the text and image consistency and structural coherence of generated images, revealing the effectiveness of our test-time prompt optimization strategy. The code is available at https://github.com/27yw/GenPilot."
}